Maybe not just another checkpoint merge. My goal was to keep details as crispy clean as possible without looking like the typical 2.5d models out there. It focuses on keeping anatomy consistent and reliable while cleaning up details and producing less... nonsense.
VAE is NOT baked into the model. Suggest to use SDXL_VAE.safetensors
Alternatively, try out SDXL Anime VAE decoder Only B1.safetensors
🎛 Recommended Settings
Sampler: DPM++ 2M, DPM++ SDE, DPM++ 2S a, Euler a
Scheduler: Karras, SGM Uniform
CFG: 4-7 (idk, go wild)
Steps: lots, probably
Hires fix: yes, do it.
At the end of the day, it's an Illustrious model. All your characters and artist tags work for influencing the generation just as they would on the base model.
What I like to do? Generate the base image, use face detailer, upscale with hires fix, then run it through img2img with the same prompt at like 0.2-0.3 denoise strength
Lyrixa v1.1
Like v1.0 but better. Lighting, details, saturation, cohesion.
Lyrixa v1.0
We started here. Probably.
Description
FAQ
Comments (3)
I don't know what magic ingredient you added, but this model blew me away.
Might be useful to mention no vae is baked into the model, and suggestions for which one to use. The one I picked might have oversaturated the images.
Thank you for the feedback! Will definitely include in the description that vae isn't baked, and I'll look into baking it for the next version. Thanks again!
i really like it so far after a few test. can generate good looking womans and mans while staying true to the prompts.